Efficacy of Early Warning Scores as the Prediction Tool for Detecting Patients With Acute Deterioration in a High...

Background Early detection and response to patient deterioration are essential to prevent serious outcomes such as unplanned intensive care unit (ICU) transfers and cardiac arrests. Rapid response systems (RRS) have been implemented globally, leading to a reduction in in-hospital mortality. In high-dependency units (HDUs), where patient monitoring is more frequent than in general wards, but staffing levels are lower than in intensive care units (ICUs), the challenge of identifying deteriorating patients persists. The Early Warning Score System (EWSS), including the National EWS (NEWS) and the artificial intelligence (AI)-based Visensia Safety Index (VSI), offer tools for early detection of patients' exacerbations. This study evaluates the effectiveness of NEWS and VSI in predicting patient deterioration in an HDU in Japan. Methods This single-center retrospective cohort study was conducted at a 344-bed acute care hospital. The study population included patients admitted to the HDU between September 27, 2019, and December 31, 2019. Study outcomes were unexpected ICU admission, endotracheal intubation, de novo use of vasopressors, de novo use of non-invasive positive pressure ventilation (NPPV), cardiac arrest, and the composite outcome (any of these outcomes). The predictive accuracy of the National Early Warning Score (NEWS) and the Visensia Safety Index (VSI) for detecting outcomes within 24 hours from each time point was analyzed. Results A total of 356 patients were included, with a median age of 76 years old (interquartile range (IQR): 64-84) and a median HDU stay of 2.0 days (IQR: 2.0-3.0). Among the 2648 analyzed vital sign sets, the median NEWS score was 5.0 (IQR: 3.0-7.0) and the median VSI score was 1.1 (IQR: 0.7-1.9). Twenty-six patients (7.3%) experienced outcomes. Among these, 13 (3.7%) required unexpected ICU transfers, 6 (1.7%) required endotracheal intubation, 15 (4.2%) required de novo vasopressor use, and 7 (2.0%) required de novo NPPV. NEWS could predict unexpected ICU admissions with good accuracy (the area under the curve (AUC) 0.834), as well as de novo vasopressor use (AUC 0.765) and the composite outcome (AUC 0.701). VSI also demonstrated modest predictive efficacy for unexpected ICU transfers (AUC 0.767), endotracheal intubation (AUC 0.712), and de novo vasopressor use (AUC 0.733). Based on ROC analysis, the appropriate threshold for NEWS ranged between 6.0 and 8.0, and the optimal threshold for VSI was found to be 1.5. Chronologically, NEWS remained stable before the occurrence of outcomes, whereas VSI showed a significant upward trend, suggesting that VSI may be more sensitive to detecting early deterioration. Conclusions In this study, both NEWS and VSI demonstrated modest accuracy in predicting unexpected ICU admission and vasopressor use in an HDU. While NEWS high risk (7≥) is an appropriate cutoff value for detecting adverse outcomes, particularly lowering the VSI cutoff to 1.5, may enhance the identification of high-risk patients.